Skip to content

CGQI

Menu

Product portfolio

Capital Quant

Build, test and refine quantitative strategies for equities and digital assets.

Home   /   Products   /   Capital Quant

Research worksheets arranged by period for model testing

Product focus

Factor research and strategy backtesting

Capital Quant integrates multidimensional financial data, AI factor analysis, historical strategy backtesting and quantitative model research. Users can construct, test and refine strategies around their own research questions.

A starting question for this workflow is How does a strategy behave on historical data?

Capabilities

From hypothesis to backtest

Define a factor

Select a financial data input and use factor analysis to define the signal to investigate.

Test the strategy

Build a strategy around the signal and test it against historical observations.

Review the results

Compare results, revisit the assumptions and refine the quantitative model.

Illustrative workflow

Test a monthly equity factor

Required inputs

A dated investment universe, financial observations with release times, rebalance dates and a cost assumption.

Method

Rank the universe using only data available on each date. Set the rule in an earlier window and examine it in a later one.

What to record

An out-of-sample result with turnover, drawdown and a record of how the conclusion changes when costs rise.

Would the factor have been visible at the time?

A backtest can use the right formula and still have the wrong information. Start by rebuilding what a researcher could actually have known on each test date.

Read the research note